Color analytics for a digital image
View Patent ↗In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, determining intrinsic component information as a function of spatio-spectral information for the image, and calculating analytical information, as a function of the intrinsic component information.
1. An automated, computerized method for processing an image, comprising the steps of:
providing an image file depicting an image, in a computer memory;
determining multi-band intrinsic component information as a function of spatio-spectral information for intrinsic material and illumination for surfaces depicted in the image, expressed in a spatial extent of spectral characteristics; and
calculating analytical information as a function of indicia of scene color characteristics expressed by the multi-band intrinsic component information.
2. The method of claim 1 including the additional step of displaying the calculated analytical information.
3. The method of claim 1 wherein the intrinsic component information comprises an illumination image.
4. The method of claim 3 wherein the step of calculating analytical information, as a function of the intrinsic component information, is carried out by calculating an illumination intensity histogram of the illumination image.
5. The method of claim 4 including the additional step of calculating a shadow depth indication as a function of the illumination intensity histogram.
6. The method of claim 3 wherein the illumination image comprises a representation of illumination, expressed as a separate, multi-band representation of illumination, independent of material.
7. The method of claim 1 wherein the spatio-spectral information comprises a characteristic spectral ratio.
8. The method of claim 7 wherein the step of calculating analytical information, as a function of the intrinsic component information, is carried out by using intrinsic component information inherent in the characteristic spectral ratio to represent relative fill light color.
9. The method as recited in claim 7 wherein the characteristic spectral ratio is expressed by a ratio of the color on one side of an illumination boundary and the color on the other side of the illumination boundary.
10. The method as recited in claim 9 wherein the image is illuminated by ambient illumination on the one side and the image is illuminated by the ambient illumination and direct illumination on the other side.
11. The method of claim 1 wherein the step of determining intrinsic component information as a function of spatio-spectral information for the image is carried out by determining intrinsic component information relative to a face depicted in the image.
12. The method of claim 1 wherein the determining multi-band intrinsic component information includes executing a spatio-spectral operator/constraint/solver model utilizing spectral relationships among contiguous pixels, in terms of color bands, and the spatial extent of the pixel spectral characteristics relevant to a single material depicted in the image or illumination flux effecting the image.
13. The method as recited in claim 12 wherein the executing a spatio-spectral operator/constraint/solver model includes utilizing a bi-illuminant dichromatic reflection model for image segregation.
14. The method as recited in claim 12 wherein the executing a spatio-spectral operator/constraint/solver model includes generating spatio-spectral operators for the image and defining a constraint between the spatio-spectral operators.
15. The method as recited in claim 12 wherein the spatio-spectral operator/constraint/solver model utilizes a relationship expressed as: I=ML, where I is a recorded image color of the transmitted image, M is the material component of the recorded image color and L the illumination component of the recorded image color.
16. The method as recited in claim 12 wherein the executing a spatio-spectral operator/constraint/solver model includes utilizing a spectral ratio based upon a difference in color or intensities between two areas of a scene depicted in an image caused by at least one of different materials and an illumination change for image segregation.
17. A computer system which comprises:
a CPU; and
a memory storing an image file containing an image;
the CPU arranged and configured to execute a routine to determine multi-band intrinsic component information as a function of spatio-spectral information for intrinsic material and illumination for surfaces depicted in the image, expressed in a spatial extent of spectral characteristics, and calculate analytical information as a function of indicia of scene color characteristics expressed by the multi-band intrinsic component information.
18. A computer program product, disposed on a non-transitory computer readable media, the product including computer executable process steps operable to control a computer to: provide an image file depicting an image, in a computer memory, determine multi-band intrinsic component information as a function of spatio-spectral information for intrinsic material and illumination for surfaces depicted in the image, expressed in a spatial extent of spectral characteristics, and calculate analytical information as a function of indicia of scene color characteristics expressed by the multi-band intrinsic component information.
19. The computer program product of claim 18 including the further process step of displaying the calculated analytical information.
20. The computer program product of claim 18 wherein the multi-band intrinsic component information comprises a multi-band illumination image.
21. The computer program product of claim 20 wherein the process step to calculate analytical information, as a function of the multi-band intrinsic component information, is carried out by calculating an illumination intensity histogram of the multi-band illumination image.
22. The computer program product of claim 21 including the additional process step of calculating a shadow depth indication as a function of the illumination intensity histogram.
23. The computer program product of claim 18 wherein the spatio-spectral information comprises a characteristic spectral ratio.
24. The computer program product of claim 23 wherein the process step to calculate analytical information, as a function of the multi-band intrinsic component information, is carried out by using multi-band intrinsic component information inherent in the characteristic spectral ratio to represent relative fill light color.
25. The computer program product of claim 18 wherein the process step to determine multi-band intrinsic component information as a function of spatio-spectral information for the image is carried out by determining multi-band intrinsic component information relative to a face depicted in the image.
26. A device comprising:
a CPU;
a memory storing an image file containing an image;
the CPU arranged and configured to execute a routine to determine multi-band intrinsic component information as a function of spatio-spectral information for intrinsic material and illumination for surfaces depicted in the image, expressed in a spatial extent of spectral characteristics, and calculate analytical information as a function of indicia of scene color characteristics expressed by the multi-band intrinsic component information; and
a display, coupled to the CPU, for display of the analytical information.
27. The device of claim 26 wherein the CPU 12 executes the step to determine multi-band intrinsic component information as a function of spatio-spectral information for the image by determining multi-band intrinsic component information relative to a face depicted in the image.